INDEX

Explanations

phrases related to guidance, persuasion, or decision-making

oai_token-act-pair · gpt-3.5-turbo

specific emotional indicators or expressions of urgency

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mathemat

-0.74

 Jericho

-0.73

Sag

-0.69

 Naked

-0.69

 fortun

-0.69

 Shap

-0.66

Tek

-0.63

 Voyager

-0.62

 Forth

-0.61

 chart

-0.61

POSITIVE LOGITS

Ļ

1.35

¬

1.21

ľ

1.14

Â¢

1.12

ı

1.11

>>

1.09

ĸ

1.08

Ħ¢

1.07

--+

1.05

âĪĴ

1.04

Activations Density 0.408%

phrases related to guidance, persuasion, or decision-making

specific emotional indicators or expressions of urgency

No Comments

No Known Activations